Catálogo de publicaciones - libros

Although there are many efforts for automated semantic web service composition, most of them are based upon the traditional AI planning techniques. Openness and dynamics of the Web environment limits the usage of previous approaches based upon the traditional AI planning techniques. This paper introduces a BDI agent system for semantic web service composition and invocation. Through some tests on healthcare web services, we found our BDI agent approach has the potential enough to improve robustness and flexibility of semantic web services.

We have developed a home-computer based system, addressing important aspects of the development of contemporary home — care that comprises of first, the employment of low-cost commercially available components, supporting home-care patient’s well-being observation, including eventually vital-signs monitoring, and, second, software means for the processing, the evaluation and the targeted transmission of the acquired health-data, together with the home-care patient administration,. The hardware of the system comprises of, first, a custom-made ECG acquisition module, equipped with a RF link between amplifier and PC, second, a Nellcor finger pulse oximetry probe for typical plethysmography based Oxygen Saturation (SpO2) measurements and the estimation of Heart Rate (HR) and Respiration Rate (RR), and third, another custom-made Carotid Sounds (CS) acquisition module, for the extraction of Heart Rate (HR) and Respiration Rate (RR). The acquired row data and trends of SpO2, HR, RR, ECG waveforms, Oxygen Therapy advice etc. are appropriately processed to produce decision supportive data, while they can be easily stored in the home computer and / or transmitted to another location. The transmission can be achieved through wireless point-to-point links, modem and telephone lines on both, landlines and mobile cellular telephone lines, by a designated location through secured paths over the internet and, finally, through two satellite communication links. The pulse oximetry module is employed only if the patient is in need of Oxygen Therapy.

Query based duplex vital signal monitoring system using wireless sensor network for Ubiquitous Healthcare was designed and tested. In this system, a wireless sensor network node attached on the human body provides sensor signal of an ECG (Electrocardiogram) and body temperature from multiple patients using wireless sensor network technology. A mote-based 3-lead ECG and body temperature monitoring system operating in wireless sensor network nodes was developed. The signal from sensors first is amplified with low noise instrument amplifier, and output of which is then fed to data acquisition board for connectivity to the sensor node. Vital signal from multiple patients can be relayed using an adaptive, multi-hop routing scheme to a wired base-station. The sampled signal will be filled in the form of packets for transmission using Zigbee compatible IEEE 802.15.4 standard wireless communication. The patients will be identified by the unique id assigned to the each mote. Among various existing routing protocols, presently simple variant of DSDV algorithm with a single destination node (the base-station) has being used for routing and transmission. Each mote in network simultaneously acts as transmitter, receiver and a router.

Assessment of automatic nerve activity is thought to be useful for health control and assessment of workload. The purpose of this study is to clarify the assessment method of automatic nerve activity. Here electrocardiogram (ECG) and respirogram using respiratory band were measured for the analysis of automatic nerve activity. Both respiratory and heart control system were influenced by automatic nerve activity, and they have strong relationship. We tried to analyze automatic nerve activity by analyzing the relationship between heart and respiratory system using multivariable auto regressive model.

Laboratory information System (LIS) is a key tool for management of laboratory data and for improvement of service quality in clinical pathology. But various type, complexity, and large quantity of specimen, occur missing the specimen or report. So we suggest the RFID based LIS system. We developed implementation LIS system has better CQI(Continuous Quality Improvement) using RFID and XML, ADO.net, ASP.net c# 2.0. RFID technology replaces to an existing the bar-code system. Also for more convenience, we used PDA RFID module. The LIS system consists of Main Server, SQL 2005, event display and analysis web page developed using asp.net 2.0 and sharing specimen data information using XML technology.

Patients suffer from chronic disease have cost considerable social and medical expanse, it is necessary to provide them with health education both on the prevention and treatment of chronic diseases. Nowadays, digital learning platform is an excellent channel for convey multimedia enriched content to the people. This research builds a web-based diabetes health education platform and conduct further study on the learner behaviors in this platform. The proposed digital learning platform can log, analyze, predicate, and retrieve the learner behavior. The learner behavior sequence is logged and then analyzed using a sequence learning algorithm. When a new learner enter the platform, it is possible to predict the intention of the learner and thus provide the interested content to him immediately. The proposed architecture had been tested on the diabetes health education for 150 people. The experimental result showed that users were satisfied with the platform and the learning effect improved significantly. With the encouraging results, it will be feasible to apply proposed methodology to other learning courses for a better achievement of popular health.

In this paper natural immune system and artificial immune system are described. Natural immune system is an example of evolutionary learning mechanism which possesses a content addressable memory and the ability to forget little-used information, it is highly complicated and appears to be precisely turned to the problem of detecting and eliminating infection. A novel information processing system inspired by immune system of human and other animals, the artificial immune system is introduced in this paper, AIS is a computational system designed on the principles of natural immune system, which is highly distributed, adaptive and diverse system. AIS research, being interdisciplinary, demands significant knowledge of immunology and computational science. Due to the different in the nature of two fields, researchers in either field face difficulties in having mutual understanding and effectively contributing for AIS research. The paper reviews the mechanism of immune system, the basis of artificial immune system, its development history, content of research and Immune Engineering which is applied in processing control. And a major method of AIS is described, so that it explains to how to set up artificial immune network and system models. The AIS is an example of a system developed around the current understanding of the immune system. It has proved artificial immune system can capture the basic elements of the immune system and exhibit some of its chief characteristics. Through this paper, we know it is more suitable than simulated annealing and genetic algorithms for solving problem. At last, the disadvantage of AIS and the development tendency are discussed.

We have created a special software for the establishment of hospital statistical database to be used for patient records in order to improve the hospital statistics, and facilitate physicians’ and information managers’ work.

Since 2002, the software has been used successfully in several larger hospitals of Mongolia. By inputting the patients history records into the hospital statistical software, there will be an electronic database available for each patient.

Mongolian people lack of quality and timely medical diagnosis. One of main causes of poor diagnosis is lack capacity of health personnel, modern equipment and effective means of communication. The government of Mongolia considers that the quality and accessibility of medical services may be improved through establishing an integrated network of medical imaging diagnosis system and medical information network services among health institutions. In addition, these institutions will provide technical support, referral services and contribute to research and development in health sector. In Mongolia with sparsely located population and service providers, a medical imaging diagnosis system that is connected district level hospitals and with key medical institutions through integrated services digital network (ISDN) line is one of most efficient options.

In this paper we will present a fully implantable, pre-programmable stimulator with bi-directional communication still small enough for implantation in mice. The diameter of the stimulator is 12.5 mm prior to encapsulation. It can deliver stimulation pulses at a constant frequency and burst-like stimulation patterns with adjustable ON/OFF times. ON/OFF times and stimulation frequencies of up to 8 stimulation programs are stored in EEPROM prior to production of the device. The stimulation amplitude is adjustable and can be set by the user at any time. Stimulation program and amplitude are selectable by means of light-flashes through the skin. Information can be transferred back through the skin with a powerful light emitting diode. The stimulator can have a constant voltage or constant current output-stage and produces monophasic rectangular pulses at multiples of 122µs pulsewidth. Depending on the battery used, the device will work for a minimum time of three weeks if continuous stimulation with a stimulation frequency of 40 Hz is used. The device is built from commercially available surface mount components and is encapsulated by a coating of biocompatible silicone rubber. Use of modern microelectronics allowed us to develop a versatile and highly customizable stimulator that can easily be adapted for different applications. We believe this to be one of a few devices featuring adjustable output-amplitudes, selectable stimulation programs and bi-directional communication at a size that can be implanted into mice. Moreover, the use of standard-components allows the device to be built on a laboratory bench. In a preliminary short-term trial the devices performed well for one week. The ability to adjust the stimulation-amplitude will — especially in mice due the close proximity of other excitable structures — allow better selectivity of motor nerve stimulation and can avoid the problem of spread of current to adjacent sensory or motor nerves.